Search Results (1,273)

Recent advancements in Earth observation technologies have accelerated remote sensing (RS) data acquisition, yet cross-domain semantic segmentation remains challenged by domain shifts. Traditional unsupervised domain adaptation (UDA) methods often rely on computationally intensive and unstable generative adversarial networks (GANs). This study introduces elevation-aware domain adaptation (EADA), a multi-task framework that integrates elevation estimation (via digital surface models) with semantic segmentation to address distribution discrepancies. EADA employs a shared encoder and task-specific decoders, enhanced by a spatial attention-based feature fusion module. Experiments on Potsdam and Vaihingen datasets under cross-domain settings (e.g., Potsdam IRRG → Vaihingen IRRG) show that EADA achieves state-of-the-art performance, with a mean IoU of 54.62% and an F1-score of 65.47%, outperforming single-stage baselines. Elevation awareness significantly improves the segmentation of height-sensitive classes, such as buildings, while maintaining computational efficiency. Compared to multi-stage approaches, EADA’s end-to-end design reduces training complexity without sacrificing accuracy. These results demonstrate that incorporating elevation data effectively mitigates domain shifts in RS imagery. However, lower accuracy for elevation-insensitive classes suggests the need for further refinement to enhance overall generalizability. Full article

With the increasing application of sodium-ion batteries in energy storage systems, accurate state of charge (SOC) estimation plays a vital role in ensuring both available battery capacity and operational safety. Traditional Kalman-filter-based methods often suffer from limited model expressiveness or oversimplified physical assumptions, making it difficult to balance accuracy and robustness under complex operating conditions, which may lead to unreliable estimation results. To address these challenges, this paper proposes a hybrid framework that combines an unscented Kalman filter (UKF) with a long short-term memory (LSTM) neural network for SOC estimation. Under various driving conditions, the UKF—based on a second-order equivalent circuit model with online parameter identification—provides physically interpretable estimates, while LSTM effectively captures complex temporal dependencies. Experimental results under CLTC, NEDC, and WLTC cycles demonstrate that the proposed LSTM-UKF approach reduces the mean absolute error (MAE) by an average of 2% and the root mean square error (RMSE) by an average of 3% compared to standalone methods. The proposed framework exhibits excellent adaptability across different scenarios, offering a precise, stable, and robust solution for SOC estimation in sodium-ion batteries. Full article

Accurate State of Charge (SOC) estimation is challenged by battery aging and complex internal dynamics. This work introduces a novel framework, Mamba-PG, that leverages the Mamba architecture to integrate internal gas pressure—a direct indicator of electrochemical state—for high-accuracy SOC estimation. The core innovation is a specialized pressure-aware gating mechanism designed to adaptively fuse the pressure signal with conventional electrical data. On a public dataset, our model achieved a state-of-the-art Mean Absolute Error (MAE) of 0.386%. Furthermore, we demonstrate that the gating mechanism learns a physically-plausible and interpretable strategy, dynamically adjusting the pressure signal’s influence based on its magnitude and the battery’s aging state. This study validates that the synergy of novel physical signals with efficient, interpretable architectures like Mamba presents a robust path toward next-generation Battery Management Systems. Full article

Multi-modal remote sensing image (MRSI) matching suffers from severe nonlinear radiometric distortions and geometric deformations, and conventional feature-based techniques are generally ineffective. This study proposes a novel and robust MRSI matching method using the side window filter (MSWF). First, a novel side window scale space is constructed based on the side window filter (SWF), which can preserve shared image contours and facilitate the extraction of feature points within this newly defined scale space. Second, noise thresholds in phase congruency (PC) computation are adaptively refined with the Weibull distribution; weighted phase features are then exploited to determine the principal orientation of each point, from which a maximum index map (MIM) descriptor is constructed. Third, coarse position, orientation, and scale information obtained through global matching are employed to estimate image-pair geometry, after which descriptors are recalculated for precise correspondence search. MSWF is benchmarked against eight state-of-the-art multi-modal methods—six hand-crafted (PSO-SIFT, LGHD, RIFT, RIFT2, HAPCG, COFSM) and two learning-based (CMM-Net, RedFeat) methods—on three public datasets. Experiments demonstrate that MSWF consistently achieves the highest number of correct matches (NCM) and the highest rate of correct matches (RCM) while delivering the lowest root mean square error (RMSE), confirming its superiority for challenging MRSI registration tasks. Full article

Understanding how flowering phenology varies across spatial scales is essential for assessing plant responses to environmental heterogeneity under climate change. In this study, we investigated the flowering phenology of the plant species Taraxacum officinale across five sites in an agricultural region of Wanju, Republic of Korea. Each site contained five 1 m × 1 m quadrats, where the number of flowering heads was recorded at 1- to 2-day intervals during the spring flowering period (February to May). We applied the nlstimedist package in R to model flowering distributions and to estimate key phenological metrics including flowering onset (5%), peak (50%), and end (95%). The results revealed substantial variation in flowering timing and duration at both the intra-site (quadrat-level) and inter-site (site-level) scales. Across all sites, the mean onset, peak, end, and duration of flowering were day of year (DOY) 89.6, 101.5, 117.6, and 28.0, respectively. Although flowering onset showed relatively small variation across sites (DOY 88 to 92), flowering peak (DOY 97 to 108) and end dates (DOY 105 to 128) exhibited larger differences at the site level. Sites with dry soils and regularly mowed Zoysia japonica vegetation with minimal understory exhibited shorter flowering durations, while those with moist soils, complex microtopography, and diverse slope orientations showed delayed and prolonged flowering. These findings suggest that microhabitat variability—including landform type, slope direction, soil water content, and soil temperature—plays a key role in shaping local flowering dynamics. Recognizing this fine-scale heterogeneity is essential for improving phenological models and informing site-specific climate adaptation strategies. Full article

Previous work used machine learning (ML) to estimate past and current alfalfa yields and showed that domain adaptation (DA) with data synthesis shows promise in classifying yields as high, medium, or low. The current work uses similar techniques to forecast future alfalfa yields. A novel technique is proposed for forecasting alfalfa time series data that exploits stationarity and predicts differences in yields rather than the yields themselves. This forecasting technique generally provides more accurate forecasts than the established ARIMA family of forecasters for both univariate and multivariate time series. Furthermore, this ML-based technique is potentially easier to use than the ARIMA family of models. Also, previous work is extended by showing that DA with data synthesis also works well for predicting continuous values, not just for classification. The novel scale-invariant tabular synthesizer (SITS) is proposed, and it is competitive with or superior to other established synthesizers in producing data that trains strong models. This synthesis algorithm leads to R scores over 100% higher than an established synthesizer in this domain, while ML-based forecasters beat the ARIMA family with symmetric mean absolute percent error (sMAPE) scores as low as 12.81%. Finally, ML-based forecasting is combined with DA (ForDA) to create a novel pipeline that improves forecast accuracy with sMAPE scores as low as 9.81%. As alfalfa is crucial to the global food supply, and as climate change creates challenges with managing alfalfa, this work hopes to help address those challenges and contribute to the field of ML. Full article

Traditional cuff-based blood pressure (BP) monitoring methods provide only intermittent readings, while invasive alternatives pose clinical risks. Recent studies have demonstrated feasibility of estimating continuous non-invasive cuff-less BP using photoplethysmogram (PPG) signals alone. However, existing approaches rely on complex manual feature engineering and/or multiple model architectures, resulting in inefficient epoch training numbers and limited performance. This research proposes cBP-Tnet, an efficient single-channel and model multi-task Transformer network designed for PPG signal automatic feature extraction. cBP-Tnet employed specialized hyperparameters—integrating adaptive Kalman filtering, outlier elimination, signal synchronization, and data augmentation—leveraging multi-head self-attention and multi-task learning strategies to identify subtle and shared waveform patterns associated with systolic blood pressure (SBP) and diastolic blood pressure (DBP). We used the MIMIC-II public dataset (500 patients with 202,956 samples) for experimentation. Results showed mean absolute errors of 4.32 mmHg for SBP and 2.18 mmHg for DBP. For the first time, both SBP and DBP meet the Association for the Advancement of Medical Instrumentation’s international standard (<5 mmHg, >85 subjects). Furthermore, the network efficiently reduces the epoch training number by 13.67% when compared to other deep learning methods. Thus, this establishes cBP-Tnet’s potential for integration into wearable and home-based healthcare devices with continuous non-invasive cuff-less blood pressure monitoring. Full article

Adaptive digital back-propagation (A-DBP) is a promising candidate for mitigating Kerr nonlinearity due to its ability to estimate the optimal nonlinear scaling factor adaptively. However, the adaptive process relying on the gradient-dependent algorithm is prone to fluctuation, leading to extra iterations or even divergence and resulting in huge computational efforts in A-DBP. In this paper, an improved A-DBP algorithm with long-term memory (LTM) is proposed, employing root mean square propagation (RMSProp) to achieve low-complexity and high-robustness compensation performances. The A-DBP-LTM algorithm based on RMSProp was numerically validated through the simulated transmission of 69 Gbaud DP-16QAM over 2000 km and further verified through an experiment involving 26-λ 63 Gbaud DP-16QAM transmission over 1200 km. Compared with conventional digital back-propagation and A-DBP based on a gradient-descent algorithm, our proposed method allows substantial complexity reductions of 31.35% and 58.47%, respectively. Furthermore, high robustness in only a few iterations and a 0.33 dB improvement in the optical signal–noise ratio penalty were also experimentally demonstrated. Full article

Mangrove forests serve as critical ecological barriers in coastal zones and play a vital role in global blue carbon sequestration strategies. In recent decades, China’s mangrove ecosystems have experienced complex interactions between degradation and restoration under intense coastal urbanization and systematic conservation efforts. However, the long-term spatiotemporal patterns and driving mechanisms of mangrove ecosystem health changes remain insufficiently quantified. This study developed a multi-temporal analytical framework using Landsat imagery (1986–2021) to derive kernel normalized difference vegetation index (kNDVI) time series—an advanced phenological indicator with enhanced sensitivity to vegetation dynamics. We systematically characterized mangrove growth patterns along China’s southeastern coast through integrated Theil–Sen slope estimation, Mann–Kendall trend analysis, and Hurst exponent forecasting. A Deep Forest regression model was subsequently applied to quantify the relative contributions of environmental drivers (mean annual sea surface temperature, precipitation, air temperature, tropical cyclone frequency, and relative sea-level rise rate) and anthropogenic pressures (nighttime light index). The results showed the following: (1) a nationally significant improvement in mangrove vitality (p < 0.05), with mean annual kNDVI increasing by 0.0072/yr during 1986–2021; (2) spatially divergent trajectories, with 58.68% of mangroves exhibiting significant improvement (p < 0.05), which was 2.89 times higher than the proportion of degraded areas (15.10%); (3) Hurst persistence analysis (H = 0.896) indicating that 74.97% of the mangrove regions were likely to maintain their growth trends, while 15.07% of the coastal zones faced potential degradation risks; and (4) Deep Forest regression id the relative rate of sea-level rise (importance = 0.91) and anthropogenic (nighttime light index, importance = 0.81) as dominant drivers, surpassing climatic factors. This study provides the first national-scale, 30 m resolution assessment of mangrove growth dynamics using kNDVI, offering a scientific basis for adaptive management and blue carbon strategies in subtropical coastal ecosystems. Full article

Accurate estimation of stem profiles is critical for forest management, timber yield prediction, and ecological modeling. However, traditional taper equations often fail to capture species-specific growth variability and exhibit significant biases, particularly in the upper stem regions. Machine learning regression models were applied to estimate Quercus mongolica stem profiles across South Korea, and performance was compared with that of a traditional taper equation. A total of 2503 sample trees were used to train and validate Random Forest (RF), XGBoost (XGB), Artificial Neural Network (ANN), and Support Vector Regression (SVR) models. Predictive performance was evaluated using root mean square error, mean absolute error, and coefficient of determination metrics, and performance differences were validated statistically. The ANN model exhibited the highest predictive accuracy and stability across all diameter classes, maintaining smooth and consistent stem profiles even in the upper stem regions where the traditional taper model exhibited significant errors. RF and XGB models had moderate performance but exhibited localized fluctuations, whereas the Kozak taper equation tended to overestimate basal diameters and underestimate crown-top diameters. Machine learning models, particularly ANN, offer a robust alternative to fixed-form taper equations, contributing substantially to forest resource inventory, carbon stock assessment, and climate-adaptive forest management planning. Full article

Robotic-assisted therapy is an increasingly vital approach for upper-limb rehabilitation, offering consistent, high-intensity training critical to neuroplastic recovery. However, current control strategies often lack robustness against uncertainties and external disturbances, limiting their efficacy in dynamic, real-world settings. Addressing this gap, this study proposes a novel control framework for the iTbot—a 2-DoF end-effector rehabilitation robot—by integrating differential flatness theory with a derivative-free Kalman filter (DFK). The objective is to achieve accurate and adaptive trajectory tracking in the presence of unmeasured dynamics and human–robot interaction forces. The control design reformulates the nonlinear joint-space dynamics into a 0-flat canonical form, enabling real-time computation of feedforward control laws based solely on flat outputs and their derivatives. Simultaneously, the DFK-based observer estimates external perturbations and unmeasured states without requiring derivative calculations, allowing for online disturbance compensation. Extensive simulations across nominal and disturbed conditions demonstrate that the proposed controller significantly outperforms conventional flatness-based control in tracking accuracy and robustness, as measured by reduced mean absolute error and standard deviation. Experimental validation under both simple and repetitive physiotherapy tasks confirms the system’s ability to maintain sub-millimeter Cartesian accuracy and sub-degree joint errors even amid dynamic perturbations. These results underscore the controller’s effectiveness in enabling compliant, safe, and disturbance-resilient rehabilitation, paving the way for broader deployment of robotic therapy in clinical and home-based environments. Full article

High-frequency (HF) communication is critical for applications such as over-the-horizon positioning and ionospheric detection. However, precise time-delay estimation in complex HF channels faces significant challenges from multipath fading, Doppler shifts, and noise. This paper proposes a Modulation Signal-based Adaptive Time-Delay Estimation (MATE) algorithm, which effectively decouples carrier and modulation signals and integrates phase-locked loop (PLL) and delay-locked loop (DLL) techniques. By leveraging the autocorrelation properties of 8PSK (Eight-Phase Shift Keying) signals, MATE compensates for carrier frequency deviations and mitigates multipath interference. Simulation results based on the Watterson channel model demonstrate that MATE achieves an average time-delay estimation error of approximately 0.01 ms with a standard deviation of approximately 0.01 ms, representing a 94.12% reduction in mean error and a 96.43% reduction in standard deviation compared to the traditional Generalized Cross-Correlation (GCC) method. Validation with actual measurement data further confirms the robustness of MATE against channel variations. MATE offers a high-precision, low-complexity solution for HF time-delay estimation, significantly benefiting applications in HF communication systems. This advancement is particularly valuable for enhancing the accuracy and reliability of time-of-arrival (TOA) detection in HF-based sensor networks and remote sensing systems. Full article

With the rapid development of wireless communication technologies and the increasing demand for efficient spectrum utilization, broadband spectrum sensing has become critical in both civilian and military fields. Detecting narrowband signals under broadband environments, especially under low-signal-to-noise-ratio (SNR) conditions, poses significant challenges due to the complexity of time–frequency features and noise interference. To this end, this study presents a signal detection model named deformable feature-enhanced network–You Only Look Once (DFN-YOLO), specifically designed for blind signal detection in broadband scenarios. The DFN-YOLO model incorporates a deformable channel feature fusion network (DCFFN), replacing the concatenate-to-fusion (C2f) module to enhance the extraction and integration of channel features. The deformable attention mechanism embedded in DCFFN adaptively focuses on critical signal regions, while the loss function is optimized to the focal scaled intersection over union (Focal_SIoU), improving detection accuracy under low-SNR conditions. To support this task, a signal detection dataset is constructed and utilized to evaluate the performance of DFN-YOLO. The experimental results for broadband time–frequency spectrograms demonstrate that DFN-YOLO achieves a mean average precision (mAP50–95) of 0.850, averaged over IoU thresholds ranging from 0.50 to 0.95 with a step of 0.05, significantly outperforming mainstream object detection models such as YOLOv8, which serves as the benchmark baseline in this study. Additionally, the model maintains an average time estimation error within $5.55\times {10}^{-5}$ s and provides preliminary center frequency estimation in the broadband spectrum. These findings underscore the strong potential of DFN-YOLO for blind signal detection in broadband environments, with significant implications for both civilian and military applications. Full article

Accurate prediction of key environmental parameters is crucial for intelligent control and optimization, yet it remains challenging due to gradient instability in deep learning models, like Long Short-Term Memory (LSTM), during time series forecasting. This study introduces a novel adaptive optimization algorithm, NadamClip, which integrates gradient clipping directly into the Nadam framework to address the trade-off between convergence efficiency and gradient explosion. NadamClip incorporates an adjustable gradient clipping threshold strategy that permits manual tuning. Through systematic experiments, we identified an optimal threshold range that effectively balances model performance and training stability, dynamically adapting to the evolving convergence characteristics of the network across different training phases. Aquaculture systems are regarded as similar to modern biomanufacturing systems. The study evaluated an aquaculture dataset for ammonia concentration prediction in aquaculture environmental control processes. NadamClip achieved outstanding results on key metrics, including a Root Mean Square Error (RMSE) of 0.2644, a Mean Absolute Error (MAE) of 0.6595, and a Coefficient of Determination (R²) score of 0.9743. Compared to existing optimizer enhancements, NadamClip pioneers the integration of gradient clipping with adaptive momentum estimation, overcoming the traditional paradigm where clipping primarily serves as an external training control rather than an intrinsic algorithmic component. This study provides a practical and reproducible optimization framework for intelligent modeling of dynamic process systems, thereby contributing to the broader advancement of machine learning methods in predictive modeling and optimization for data-driven manufacturing and environmental processes. Full article

Out-of-distribution (OOD) detection is critical for securing Internet of Things (IoT) systems, particularly in applications such as intrusion detection and device identification. However, conventional classification-based approaches struggle in IoT environments due to challenges like large class numbers and data imbalance. To address these limitations, we propose a novel framework that combines class mean clustering and a group-level feature distance loss to optimize both intra-group compactness and inter-group separability. Our framework utilizes Mahalanobis distance for robust OOD scoring and Kernel density estimation (KDE) for adaptive threshold selection, enabling precise boundary estimation under varying data distributions. Experimental results on real-world IoT datasets show that our framework outperforms baseline techniques, achieving at least a 10% improvement in AUROC and a 33% reduction in FPR95, demonstrating its scalability and effectiveness in complex, imbalanced IoT scenarios. Full article